NYC

sop-authoring

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill defines templates for SOPs that ingest external data via parameters. This creates a surface for indirect prompt injection.
  • Ingestion points: Parameters such as {pr_url}, {repository_path}, and {feature_description} in the provided examples (SKILL.md).
  • Boundary markers: Absent. The templates do not include delimiters or instructions to ignore embedded commands within the parameters.
  • Capability inventory: The skill is allowed to use Bash, Write, and Edit tools as specified in the frontmatter.
  • Sanitization: Absent. There are no instructions for validating or sanitizing the input provided to these parameters.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:15 PM